Explore the directory

A local-first control plane for running and operating models, inference runtimes, agents, tools and retrieval from one privacy-first workspace, across local and cloud environments.

• Inference

A normalized store of work context that AI accumulates and maintains on its own, injecting a company's product, code and decision history into every team member's AI so everyone works from the same context.

• Agent memory

A visible, persistent Electron browser that exposes durable, named agent workspaces over MCP, so a coding agent's browser session stays open and inspectable independently of any one AI conversation.

• Browser automation

A self-hosted, multi-tenant agent platform that combines a Python API for engineers with a drag-and-drop visual canvas for business users, backed by an event-sourced, durable execution engine.

• Agent frameworks

A single Rust binary that works like grep, but matches lines, paragraphs, JSON records or diff hunks against a plain-English question instead of a pattern, exploring the scored results live in the terminal.

• CLI tools

A local, conversational control plane that lets several AI coding models propose changes to a repository, while Fusion itself verifies and applies every change only after the user approves its exact bytes.

• Coding agents

An unofficial fork of the FreeToken local LLM inference engine that benchmarks a user's own GPU with a given model and hands back the fastest settings as a ready-to-use launch profile.

• Inference

An MCP server that connects AI assistants to three official Swiss data sources for federal law, pending legal consultations and official multilingual legal terminology.

• MCP servers

A live, auto-updated index of Claude Code extensions, hooks and plugins, refreshed from GitHub every 15 minutes.

• Curated lists

Sandboxed macOS virtual machines with a full Xcode toolchain for AI coding agents, plus a lighter Linux container mode, keeping the host machine out of reach.

• Containers

A stateless, multi-provider .NET AI gateway exposing normalized OpenAI- and Anthropic-compatible endpoints, managed agents and skills across a very large catalog of models.

• LLM gateways

A collection of short, open-source guides and tutorials on AI agents, generative AI and machine learning, covering Python, TypeScript, MCP servers and clients, and Ollama integration.

• Tutorials

A Swift package providing shared system prompts, tool definitions and API provider management for macOS AI agents, giving a large set of tools a single source of truth across ten LLM providers.

• Agent frameworks

A live, auto-updated index of newly published agent framework repositories on GitHub, sorted by recency rather than popularity.

• Curated lists

An open framework for governed AI development that redacts personal data, blocks prompt injection, audits agent tool calls, and tracks EU AI Act compliance, installed as a proxy or a small Python SDK.

• AI evals
• Security

Hands-on notebooks that teach the pose-format Python library end to end, from extracting landmarks with MediaPipe to normalizing, augmenting and visualizing pose data.

• Tutorials

A terminal-first security audit toolkit that orchestrates 13 scanners across code repositories, container images, infrastructure-as-code, web apps and Kubernetes, with unified reporting.

• Security

A self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A, turning a rough request into a structured, reviewable prompt before it runs.

• LLM gateways

A secure, peer-to-peer generative AI platform that matches people who want to run LLM inference with volunteers donating their spare compute.

• Inference

An open-source CLI that benchmarks any OpenAI-compatible inference endpoint, such as vLLM, SGLang, Ollama or LMDeploy, to measure real cost per million tokens, with statistics designed not to call a winner from noisy or overlapping evidence.

• AI evals

A tool that turns a Telegram bot or group into a terminal for running OpenCode and Claude Code, so each conversation thread acts like a terminal tab you can drive from your phone by voice or text.

• Coding agents

A personal collection of agent skills for Claude Code, Codex and OpenCode, covering project setup, VS Code configuration, skill management, git commit annotations, subagent-based bug patching, UI idea exploration and a frontend design-system default.

• Agent skills

A Pharo-native tool for running and orchestrating multiple AI coding-agent sessions -- Claude Code, Gemini CLI, OpenCode and others -- in parallel from inside a Pharo Smalltalk image, with a mobile-friendly web UI.

• Coding agents

A from-scratch, cross-platform browser engine and application written in modern C++20, with a working URL-to-paint rendering pipeline and a Qt6 GUI, not a WebView wrapper or a toy HTML renderer.

• Desktop